CLAug 9, 2019
UdS Submission for the WMT 19 Automatic Post-Editing Task
arXiv:1908.03402v11089 citations
AI Analysis
This work addresses automatic post-editing for machine translation, but it appears incremental as it adapts existing methods to a specific task.
The paper tackled the English-German automatic post-editing task at WMT 2019 by adapting an NMT architecture for context information to APE, implementing a transformer model, and exploring joint training with a de-noising encoder, but no concrete results or numbers are reported.
In this paper, we describe our submission to the English-German APE shared task at WMT 2019. We utilize and adapt an NMT architecture originally developed for exploiting context information to APE, implement this in our own transformer model and explore joint training of the APE task with a de-noising encoder.